Skip to content
VECTOR WIREAI INTELLIGENCE
⌘K
UTC
Models741Deals30d271Policy30d66, 14 pendingSources1,015

DeepSeek-R1 vs DeepSeek-V3

DeepSeek · released

Wins 4 of 6 areas

Coding · Agents · Reasoning · Long documents

DeepSeek · released

Wins 1 of 6 areas

Facts

DeepSeek-R1 is the stronger all-rounder.DeepSeek-V3 is cheaper and better at facts.

Scores updated · 55 tests both models report · How we compare

Where each one wins

Tests won in each of the six areas where both have results. Each piece is one test, so a longer bar means more evidence; grey means the two scored within a point of each other.

What it costs

Prices per million tokens, roughly 750,000 words. The bars show the cost of a million tokens read plus a million written.

DeepSeek-R1$2.00 to read · $4.00 to write$6.00Price from Artificial Analysis
DeepSeek-V3$0.24 to read · $0.90 to write$1.14Price from Artificial Analysis

DeepSeek-V3 costs 81% less for the same work.

The biggest differences

The three tests each model wins by the widest margin. Scores are out of 100.

Where DeepSeek-R1 pulls ahead

  • Reasons across sets of long documentsAA-LCR+17points aheadDeepSeek-R157.7DeepSeek-V340.7
  • Questions about very long textsLongBench v2+9.6points aheadDeepSeek-R158.3DeepSeek-V348.7
  • Keeps track of context across a multi-turn chatMulti-Challenge+9.3points aheadDeepSeek-R140.7DeepSeek-V331.4

Where DeepSeek-V3 pulls ahead

  • Hard command-line tasks in a real terminalTerminal-Bench Hard+9.1points aheadDeepSeek-V315.2DeepSeek-R16.1
  • Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+4.4points aheadDeepSeek-V314.1DeepSeek-R19.7
  • Follows unfamiliar, precisely checkable instructionsIFBench+2points aheadDeepSeek-V341DeepSeek-R139

Every test, side by side

All 55 tests both models report. The winning score is in its model's colour; marks a score checked independently.

CodingDeepSeek-R1

Full coding ranking

AgentsDeepSeek-R1

Full agents ranking

ReasoningDeepSeek-R1

Full reasoning ranking

FactsDeepSeek-V3

Full facts ranking

Long documentsDeepSeek-R1

Full long documents ranking

Following instructionsEven

Full following instructions ranking

Other results38 tests, not counted

Tests outside the eight areas. They are not counted above: several are summary scores built from other tests, or the same test under another name.

Questions people ask

Which is better, DeepSeek-R1 or DeepSeek-V3?

DeepSeek-R1 wins four of the six areas where both have results: coding, agents, reasoning and long documents. DeepSeek-V3 wins facts, and costs 81% less. They are level on following instructions.

Which is better for coding?

DeepSeek-R1. It wins 2 of the 4 coding tests both models report; DeepSeek-V3 wins 1, and 1 is a tie.

Which is cheaper?

DeepSeek-R1 costs $2.00 per million input tokens and $4.00 per million output tokens; DeepSeek-V3 costs $0.24 and $0.90. That makes DeepSeek-V3 about 81% cheaper for the same work.

How do you compare the two?

We use the 55 benchmark tests both models have published scores on. The verdict counts the 17 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 38 are listed but not counted, because several are summary scores or repeat a test. Each score is the one shown on the model's own page.

Compare DeepSeek-V3 with

DeepSeek

Across the field

All comparisons